Examples of cascading.operation.regex.RegexReplace

        List<Pipe> tailPipes = new ArrayList<Pipe>();
        
        if (options.isGenerateHTML()) {
            // Let's write out the parse as text:
            Pipe textParsePipe = new Pipe("text parse data", parsePipe.getTailPipe());
            textParsePipe = new Each(textParsePipe, new Fields(ParsedDatum.PARSED_TEXT_FN), new RegexReplace(new Fields(ParsedDatum.PARSED_TEXT_FN), "[\\r\\n\\t]+", " ", true), Fields.REPLACE);
            textParsePipe = new Each(textParsePipe, new Fields(ParsedDatum.URL_FN, ParsedDatum.PARSED_TEXT_FN), new Identity());
            BasePath textParsePath = platform.makePath(curWorkingDirPath, CrawlConfig.HTML_SUBDIR_NAME);
            Tap textParseTap = platform.makeTap(platform.makeTextScheme(), textParsePath, SinkMode.REPLACE);
            sinkMap.put(textParsePipe.getName(), textParseTap);
            tailPipes.add(textParsePipe);

      Pipe importPipe = new Each( name, new Fields( "line" ), regexSplitter );
      // remove all pdf documents from the stream
      importPipe = new Each( importPipe, new Fields( "url" ), new RegexFilter( ".*\\.pdf$", true ) );
      // replace ":nl" with a new line, return the fields "url" and "page" to the stream.
      // discared the other fields in the stream
      RegexReplace regexReplace = new RegexReplace( new Fields( "page" ), ":nl:", "\n" );
      importPipe = new Each( importPipe, new Fields( "raw" ), regexReplace, new Fields( "url", "page" ) );


      setTails( importPipe );
      }

Related Classes of cascading.operation.regex.RegexReplace

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.